Unterschiede

Hier werden die Unterschiede zwischen zwei Versionen angezeigt.

--- dienste:bytecluster0002:wiki [27.12.2020 21:30] – mape2k
+++ dienste:bytecluster0002:wiki [18.03.2024 22:10] (aktuell) – Bytespider aussperren wegen exzessiven Anfragen, Robots.txt wegen KI-Spidern mape2k
@@ Zeile 13: / Zeile 13: @@
 ===== Dienste =====
-  * FIXME
+  * Dokuwiki (via NGINX)
 ===== Installation =====
@@ Zeile 22: / Zeile 22: @@
   - NGINX und PHP-FPM installieren
-    * **sudo apt-get install php7.3 php7.3-cli php7.3-fpm php7.3-gd php7.3-xml php7.3-zip nginx**
+    * **sudo apt-get install php7.4 php7.4-cli php7.4-fpm php7.4-gd php7.4-xml php7.4-zip php7.4-mbstring nginx**
   - Default-Konfiguration anpassen<file|/etc/nginx/sites-available/default>
 server {
@@ Zeile 34: / Zeile 34: @@
 	server_name _;
+        # Block Bytespider
+        if ($http_user_agent ~ (Bytespider|bytedance) ) {
+                return 403;
+        }
 	location / {
@@ Zeile 61: / Zeile 66: @@
 	location ~ \.php$ {
 		try_files $uri =404;
-                fastcgi_pass unix:/var/run/php/php7.3-fpm.sock;
+                fastcgi_pass unix:/var/run/php/php7.4-fpm.sock;
                 fastcgi_index index.php;
                 include fastcgi_params;
@@ Zeile 69: / Zeile 74: @@
 </file>
   - Dienste aktivieren und neustarten
-    * **sudo systemctl enable nginx.service php7.3-fpm.service**
+    * **sudo systemctl enable nginx.service php7.4-fpm.service**
-    * **sudo systemctl restart nginx.service php7.3-fpm.service**
+    * **sudo systemctl restart nginx.service php7.4-fpm.service**
 ==== Dokuwiki ====
@@ Zeile 80: / Zeile 85: @@
       * Entpacken in das Verzeichnis /var/www/public_html
       * Datenverzeichnis nach /var/www/data (bzw. ../data)
+  - Berechtigungen anpassen
+    * **chown -R www-data:www-data /var/www/{public_html,data}**
   - Cache-Cleanup einrichten
     - Cleanup-Skript<file|/usr/local/bin/cleanup_dokuwiki_cache.sh>
+#!/bin/bash
+cleanup()
+{
+    local data_path="$1"        # full path to data directory of wiki
+    local retention_days="$2"   # number of days after which old files are to be removed
+    # remove stale lock files (files which are 1-2 days old)
+    find "${data_path}"/locks/ -name '*.lock' -type f -mtime +1 -delete
+    # remove files older than ${retention_days} days from the cache
+    find "${data_path}"/cache/ -type f -mtime +${retention_days} -delete
+}
+# cleanup DokuWiki installations (path to datadir, number of days)
+cleanup /var/www/data    180
 </file>
     - Cleanup-Skript ausführbar machen
@@ Zeile 87: / Zeile 110: @@
     - Cleanup-Skript als Cronjob einrichten machen
       * **<nowiki>echo -e "0 2 * * *\troot\t/usr/local/bin/cleanup_dokuwiki_cache.sh" | sudo tee /etc/cron.d/dokwiki > /dev/null/<nowiki>**
+=== robots.txt ===
+Quelle: https://neil-clarke.com/block-the-bots-that-feed-ai-models-by-scraping-your-website/
+  - Robots.txt setzen<file|/var/www/public_html/robots.txt>
+User-agent: CCBot
+Disallow: /
+User-agent: ChatGPT-User
+Disallow: /
+User-agent: GPTBot
+Disallow: /
+User-agent: Google-Extended
+Disallow: /
+User-agent: anthropic-ai
+Disallow: /
+User-agent: Omgilibot
+Disallow: /
+User-agent: Omgili
+Disallow: /
+User-agent: FacebookBot
+Disallow: /
+User-agent: Bytespider
+Disallow: /
+User-agent: ImagesiftBot
+Disallow: /
+</file>
+  - Berechtigungen anpassen
+    * **chown www-data:www-data /var/www/public_html/robots.txt**
 ==== Backup mit Borgmatic ====
@@ Zeile 99: / Zeile 161: @@
         - /home
         - /root
+        - /usr/local
         - /var/log
         - /var/www
 ...
 </file>